paper-with-me

홈 › Papers

Uncertainty quantification for learned ISTA

2023-09-14 · Frederik Hoppe, Claudio Mayrink Verdun, Felix Krahmer, Hannah Laus, Holger Rauhut

Model-based deep learning solutions to inverse problems have attracted increasing attention in recent years as they bridge state-of-the-art numerical performance with interpretability. In addition, the incorporated prior domain knowledge can make the training more efficient as the smaller number of parameters allows the training step to be executed with smaller datasets. Algorithm unrolling schemes stand out among these model-based learning techniques. Despite their rapid advancement and their close connection to traditional high-dimensional statistical methods, they lack certainty estimates and a theory for uncertainty quantification is still elusive. This work provides a step towards closing this gap proposing a rigorous way to obtain confidence intervals for the LISTA estimator.

📄 PDF Abstract BibTeX arXiv:2309.07982

Code (0)

등록된 구현이 없습니다.

Tasks

Uncertainty Quantification

Similar Papers 제목 키워드 기반

Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis

2023-03-19 · Subhankar Ghosh, Taha Belkhouja, Yan Yan, Janardhan Rao Doppa

Safe deployment of deep neural networks in high-stake real-world applications requires theoretically sound uncertainty quantification. Conformal prediction (CP) is a principled framework for uncertainty quantification of…

Conformal PredictionPredictionUncertainty Quantification

Fast Uncertainty Quantification for Deep Object Pose Estimation

2020-11-16 · Guanya Shi, Yifeng Zhu, Jonathan Tremblay, Stan Birchfield 외

Deep learning-based object pose estimators are often unreliable and overconfident especially when the input image is outside the training domain, for instance, with sim2real transfer. Efficient and robust uncertainty qua…

ObjectPose EstimationUncertainty Quantification

Streamflow Prediction with Uncertainty Quantification for Water Management: A Constrained Reasoning and Learning Approach

2024-05-31 · Mohammed Amine Gharsallaoui, Bhupinderjeet Singh, Supriya Savalkar, Aryan Deshwal 외

Predicting the spatiotemporal variation in streamflow along with uncertainty quantification enables decision-making for sustainable management of scarce water resources. Process-based hydrological models (aka physics-bas…

Decision MakingGaussian ProcessesManagementTime Series Forecasting+1

Uncertainty Quantification for Cardiac Shape Reconstruction with Deep Signed Distance Functions via MCMC methods

2026-05-08 · Jan Verhülsdonk, Thomas Grandits, Francisco Sahli Costabal, Thomas Beiert 외 arxiv

Atlas-based approaches allow high-quality, patient-specific shape reconstructions of cardiac anatomy from sparse and/or noisy data such as point clouds. However, these methods are mainly prior-driven, so the impact of un…

Bayesian InferencePoint Clouds

Is Uncertainty Quantification a Viable Alternative to Learned Deferral?

2025-08-04 · Anna M. Wundram, Christian F. Baumgartner arxiv

Artificial Intelligence (AI) holds the potential to dramatically improve patient care. However, it is not infallible, necessitating human-AI-collaboration to ensure safe implementation. One aspect of AI safety is the mod…